MATH

12,500 competition mathematics problems with step-by-step solutions, spanning algebra to number theory, for evaluating mathematical reasoning.

Papers using MATH (49)

Improved Large Language Diffusion Models2026HRM-Text: Efficient Pretraining Beyond Scaling2026Rethinking LLM-as-a-Judge: Representation-as-a-Judge with Small Language Models via Semantic Capacity Asymmetry2026Heteroskedastic Signals in Budgeted LLM Verification: Structural Heterogeneity Limits Optimization Gains2026How Should LLMs Consume High-Quality Data? Optimal Data Scheduling via Quality-Aware Functional Scaling Laws2026ReasonFlux: Hierarchical LLM Reasoning via Scaling Thought Templates2025 · 2 citesWhen Do LLM Agents Treat Surface Noise Differently from Semantic Noise? A 68-Cell Measurement Study with a Held-Out Trace-Level Validation2026Words & Weights: Streamlining Multi-Turn Interactions via Co-Adaptation2026KV-PRM: Efficient Process Reward Modeling via KV-Cache Transfer for Multi-Agent Test-Time Scaling2026Confidence Geometry Reveals Trace-Level Correctness in Large Language Model Reasoning2026Fast-dLLM++: Fr\'{e}chet Profile Decoding for Faster Diffusion LLM Inference2026Search for Truth from Reasoning: A Dynamic Representation Editing Framework for Steering LLM Trajectories2026LLMs Encode Their Failures: Predicting Success from Pre-Generation Activations2026Beyond GRPO and On-Policy Distillation: An Empirical Sparse-to-Dense Reward Principle for Language-Model Post-Training2026Off-the-Shelf LLMs as Process Scorers: Training-Free Alternative to PRMs for Mathematical Reasoning2026The Master Key Hypothesis: Unlocking Cross-Model Capability Transfer via Linear Subspace Alignment2026Learning to Predict Future-Aligned Research Proposals with Language Models2026Discovering Process-Outcome Credit in Multi-Step LLM Reasoning2026Towards Long-Horizon Interpretability: Efficient and Faithful Multi-Token Attribution for Reasoning LLMs2026Group-Aware Reinforcement Learning for Output Diversity in Large Language Models2025Can Aha Moments Be Fake? Towards Quantifying Decorative and True Thinking in Chain-of-Thought2025How to Train a Leader: Hierarchical Reasoning in Multi-Agent LLMs2025CLEAR: Error Analysis via LLM-as-a-Judge Made Easy2025Exchange of Perspective Prompting Enhances Reasoning in Large Language Models2025SIGMA: Refining Large Language Model Reasoning via Sibling-Guided Monte Carlo Augmentation2025Syzygy of Thoughts: Improving LLM CoT with the Minimal Free Resolution2025M1: Towards Scalable Test-Time Compute with Mamba Reasoning Models2025SPC: Evolving Self-Play Critic via Adversarial Games for LLM Reasoning2025SEED-GRPO: Semantic Entropy Enhanced GRPO for Uncertainty-Aware Policy Optimization2025Interleaved Reasoning for Large Language Models via Reinforcement Learning2025Aryabhata: An exam-focused language model for JEE Math2025Test-Time Scaling in Diffusion LLMs via Hidden Semi-Autoregressive Experts2025Don't Waste Mistakes: Leveraging Negative RL-Groups via Confidence Reweighting2025Shape of Thought: When Distribution Matters More than Correctness in Reasoning Tasks2025rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking2025EvalTree: Profiling Language Model Weaknesses via Hierarchical Capability Trees2025Reasoning to Learn from Latent Thoughts2025Entropy-Based Adaptive Weighting for Self-Training2025GenPRM: Scaling Test-Time Compute of Process Reward Models via Generative Reasoning2025T1: Tool-integrated Self-verification for Test-time Compute Scaling in Small Language Models2025Putting the Value Back in RL: Better Test-Time Scaling by Unifying LLM Reasoners With Verifiers2025Warm Up Before You Train: Unlocking General Reasoning in Resource-Constrained Settings2025Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoning2025Skill-Targeted Adaptive Training2025Rethinking Mixture-of-Agents: Is Mixing Different Large Language Models Beneficial?2025Self-Training Elicits Concise Reasoning in Large Language Models2025DIVE: Diversified Iterative Self-Improvement2025Dipper: Diversity in Prompts for Producing Large Language Model Ensembles in Reasoning tasks2024CodePMP: Scalable Preference Model Pretraining for Large Language Model Reasoning2024